Explainability-Driven Quality Assessment for Rule-Based Systems

TL;DR

This paper presents an explanation framework that improves rule-based systems by providing diverse interpretability methods, enabling human-guided refinement, and ensuring transparency and fairness in decision-making, demonstrated in a finance use case.

Contribution

It introduces a novel explanation framework with four explanation types to enhance rule quality and facilitate human-driven rule refinement in knowledge-based systems.

Findings

Effective in debugging and validating rules

Enhances transparency and fairness in decision-making

Demonstrated practical utility in finance domain

Abstract

This paper introduces an explanation framework designed to enhance the quality of rules in knowledge-based reasoning systems based on dataset-driven insights. The traditional method for rule induction from data typically requires labor-intensive labeling and data-driven learning. This framework provides an alternative and instead allows for the data-driven refinement of existing rules: it generates explanations of rule inferences and leverages human interpretation to refine rules. It leverages four complementary explanation types: trace-based, contextual, contrastive, and counterfactual, providing diverse perspectives for debugging, validating, and ultimately refining rules. By embedding explainability into the reasoning architecture, the framework enables knowledge engineers to address inconsistencies, optimize thresholds, and ensure fairness, transparency, and interpretability in decision-making processes. Its practicality is demonstrated through a use case in finance.